Clinical characteristics and prognostic factors for Crohn's disease relapses using natural language processing and machine learning: a pilot study

Abstract

Background: The impact of relapses on disease burden in Crohn's disease (CD) warrants searching for predictive factors to anticipate relapses. This requires analysis of large datasets, including elusive free-text annotations from electronic health records. This study aims to describe clinical characteristics and treatment with biologics of CD patients and generate a data-driven predictive model for relapse using natural language processing (NLP) and machine learning (ML).

Methods: We performed a multicenter, retrospective study using a previously validated corpus of CD patient data from eight hospitals of the Spanish National Healthcare Network from 1 January 2014 to 31 December 2018 using NLP. Predictive models were created with ML algorithms, namely, logistic regression, decision trees, and random forests.

Results: CD phenotype, analyzed in 5938 CD patients, was predominantly inflammatory, and tobacco smoking appeared as a risk factor, confirming previous clinical studies. We also documented treatments, treatment switches, and time to discontinuation in biologics-treated CD patients. We found correlations between CD and patient family history of gastrointestinal neoplasms. Our predictive model ranked 25 000 variables for their potential as risk factors for CD relapse. Of highest relative importance were past relapses and patients' age, as well as leukocyte, hemoglobin, and fibrinogen levels.

Conclusion: Through NLP, we identified variables such as smoking as a risk factor and described treatment patterns with biologics in CD patients. CD relapse prediction highlighted the importance of patients' age and some biochemistry values, though it proved highly challenging and merits the assessment of risk factors for relapse in a clinical setting.

Trial registration: ClinicalTrials.gov NCT03668249.

Conflict of interest statement

Dr. F. Gomollón has received educational grants from Janssen, MSD, Takeda, and Abbvie, and nonpersonal investigation grants from MSD, Janssen, Abbvie, Takeda, and Tilllots. Dr. J.P. Gisbert has served as a speaker, a consultant, and advisory member for, or has received research funding from, MSD, Abbvie, Hospira, Pfizer, Kern Pharma, Biogen, Takeda, Janssen, Roche, Sandoz, Celgene, Ferring, Faes Farma, Shire Pharmaceuticals, Dr. Falk Pharma, Tillotts Pharma, Chiesi, Casen Fleet, Gebro Pharma, Otsuka Pharmaceutical, and Vifor Pharma. Dr. I. Guerra has served as a speaker, a consultant, and advisory member for, or has received research funding from, Kern Pharma, Takeda and Janssen. Dr. R. Plaza has served as a speaker for Takeda and Janssen. Dr. M.I. Vera has served as a speaker, consultant, and advisory member for, or has received funding from, MSD, Abbvie, Pfizer, Ferring, Shire Pharmaceuticals, Takeda and Jannsen. Jesús Aparicio, Vicente Martínez, Ignacio Tagarro, Alonso Fernández-Nistal, and Carmen Montoto are employees at Takeda Farmacéutica España S.A. S. Lumbreras is an employee at Universidad Pontificia Comillas, Madrid. Dr. C. Maté is an employee at Medsavana S.L. The remaining authors have no conflicts of interest to declare.

Copyright © 2021 The Author(s). Published by Wolters Kluwer Health, Inc.

Figures

Fig. 1

Study design and timeline. For each patient in the database, the Index Date (i.e., Baseline) was defined as the timepoint when diagnostic criteria for CD is first identified. All available EHRs before January 2014 were handled to extract information regarding the clinical history of patients (dotted line). The follow-up period ranged from the index date to the end of the study period or the last data point available. Data from patients’ EHRs were extracted and organized with the EHRead technology. See the Methods section for further details. CD, Crohn’s disease; EHR, electronic health record.